Mercurial > repos > devteam > picard_122_up
comparison picard_ValidateSamFile.xml @ 0:b76a4f17bbbb draft
Uploaded
| author | devteam |
|---|---|
| date | Thu, 23 Oct 2014 11:31:30 -0400 |
| parents | |
| children |
comparison
equal
deleted
inserted
replaced
| -1:000000000000 | 0:b76a4f17bbbb |
|---|---|
| 1 <tool name="ValidateSamFile" id="picard_ValidateSamFile" version="1.122.0"> | |
| 2 <description>assess validity of SAM/BAM dataset</description> | |
| 3 <requirements> | |
| 4 <requirement type="package" version="1.122.0">picard</requirement> | |
| 5 </requirements> | |
| 6 | |
| 7 <macros> | |
| 8 <import>picard_macros.xml</import> | |
| 9 </macros> | |
| 10 | |
| 11 <command> | |
| 12 | |
| 13 ##set the maximum number of open file to hard maximum or 4096 if on a mac (mac gives 'unlimited' as output of `ulimit -Hn` command | |
| 14 | |
| 15 [ `ulimit -Hn` = unlimited ] && ulimit -Sn 4096 || ulimit -Sn `ulimit -Hn` | |
| 16 | |
| 17 && | |
| 18 | |
| 19 ##set up input files | |
| 20 | |
| 21 #set $reference_fasta_filename = "localref.fa" | |
| 22 | |
| 23 #if str( $reference_source.reference_source_selector ) == "history": | |
| 24 ln -s "${reference_source.ref_file}" "${reference_fasta_filename}" && | |
| 25 #else: | |
| 26 #set $reference_fasta_filename = str( $reference_source.ref_file.fields.path ) | |
| 27 #end if | |
| 28 | |
| 29 @java_options@ | |
| 30 | |
| 31 java -jar \$JAVA_JAR_PATH/ValidateSamFile.jar | |
| 32 | |
| 33 INPUT="${inputFile}" | |
| 34 OUTPUT="${outFile}" | |
| 35 MODE="${mode}" | |
| 36 | |
| 37 #if str( $ignore ) != "None": | |
| 38 #for $element in str( $ignore ).split(','): ## See trello card https://trello.com/c/9nW02Zhd | |
| 39 IGNORE="${element}" | |
| 40 #end for | |
| 41 #end if | |
| 42 | |
| 43 MAX_OUTPUT="${max_output}" | |
| 44 REFERENCE_SEQUENCE="${reference_fasta_filename}" | |
| 45 IGNORE_WARNINGS="${ignore_warnings}" | |
| 46 IS_BISULFITE_SEQUENCED="${is_bisulfite_sequenced}" | |
| 47 MAX_OPEN_TEMP_FILES=`ulimit -Sn` | |
| 48 | |
| 49 VERBOSITY=ERROR | |
| 50 QUIET=true | |
| 51 | |
| 52 </command> | |
| 53 <inputs> | |
| 54 <param format="sam,bam" name="inputFile" type="data" label="SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset." /> | |
| 55 <conditional name="reference_source"> | |
| 56 <param name="reference_source_selector" type="select" label="Load reference genome from"> | |
| 57 <option value="cached">Local cache</option> | |
| 58 <option value="history">History</option> | |
| 59 </param> | |
| 60 <when value="cached"> | |
| 61 <param name="ref_file" type="select" label="Use dictionary from the list" help="Select genome from the list"> | |
| 62 <options from_data_table="picard_indexes"> | |
| 63 <filter type="sort_by" column="2" /> | |
| 64 <validator type="no_options" message="No indexes are available" /> | |
| 65 </options> | |
| 66 <validator type="no_options" message="A built-in dictionary is not available for the build associated with the selected input file"/> | |
| 67 </param> | |
| 68 </when> | |
| 69 <when value="history"> | |
| 70 <param name="ref_file" type="data" format="fasta" label="Use the following dataset to create dictionary" help="You can upload a FASTA sequence to the history from which Picard will automatically generate dictionary using CreateSequenceDictionary command" /> | |
| 71 </when> | |
| 72 </conditional> | |
| 73 | |
| 74 <param name="mode" type="select" label="Select output mode" help="MODE"> | |
| 75 <option value="VERBOSE">Verbose</option> | |
| 76 <option value="SUMMARY">Summary</option> | |
| 77 </param> | |
| 78 <param name="ignore" type="select" multiple="true" display="checkboxes" label="Select validation error types to ignore" help="IGNORE"> | |
| 79 <option value="INVALID_QUALITY_FORMAT">INVALID_QUALITY_FORMAT</option> | |
| 80 <option value="INVALID_FLAG_PROPER_PAIR">INVALID_FLAG_PROPER_PAIR</option> | |
| 81 <option value="INVALID_FLAG_MATE_UNMAPPED"/> | |
| 82 <option value="MISMATCH_FLAG_MATE_UNMAPPED"/> | |
| 83 <option value="INVALID_FLAG_MATE_NEG_STRAND"/> | |
| 84 <option value="MISMATCH_FLAG_MATE_NEG_STRAND"/> | |
| 85 <option value="INVALID_FLAG_FIRST_OF_PAIR"/> | |
| 86 <option value="INVALID_FLAG_SECOND_OF_PAIR"/> | |
| 87 <option value="PAIRED_READ_NOT_MARKED_AS_FIRST_OR_SECOND"/> | |
| 88 <option value="INVALID_FLAG_NOT_PRIM_ALIGNMENT"/> | |
| 89 <option value="INVALID_FLAG_SUPPLEMENTARY_ALIGNMENT"/> | |
| 90 <option value="INVALID_FLAG_READ_UNMAPPED"/> | |
| 91 <option value="INVALID_INSERT_SIZE"/> | |
| 92 <option value="INVALID_MAPPING_QUALITY"/> | |
| 93 <option value="INVALID_CIGAR"/> | |
| 94 <option value="ADJACENT_INDEL_IN_CIGAR"/> | |
| 95 <option value="INVALID_MATE_REF_INDEX"/> | |
| 96 <option value="MISMATCH_MATE_REF_INDEX"/> | |
| 97 <option value="INVALID_REFERENCE_INDEX"/> | |
| 98 <option value="INVALID_ALIGNMENT_START"/> | |
| 99 <option value="MISMATCH_MATE_ALIGNMENT_START"/> | |
| 100 <option value="MATE_FIELD_MISMATCH"/> | |
| 101 <option value="INVALID_TAG_NM"/> | |
| 102 <option value="MISSING_TAG_NM"/> | |
| 103 <option value="MISSING_HEADER"/> | |
| 104 <option value="MISSING_SEQUENCE_DICTIONARY"/> | |
| 105 <option value="MISSING_READ_GROUP"/> | |
| 106 <option value="RECORD_OUT_OF_ORDER"/> | |
| 107 <option value="READ_GROUP_NOT_FOUND"/> | |
| 108 <option value="RECORD_MISSING_READ_GROUP"/> | |
| 109 <option value="INVALID_INDEXING_BIN"/> | |
| 110 <option value="MISSING_VERSION_NUMBER"/> | |
| 111 <option value="INVALID_VERSION_NUMBER"/> | |
| 112 <option value="TRUNCATED_FILE"/> | |
| 113 <option value="MISMATCH_READ_LENGTH_AND_QUALS_LENGTH"/> | |
| 114 <option value="EMPTY_READ"/> | |
| 115 <option value="CIGAR_MAPS_OFF_REFERENCE"/> | |
| 116 <option value="MISMATCH_READ_LENGTH_AND_E2_LENGTH"/> | |
| 117 <option value="MISMATCH_READ_LENGTH_AND_U2_LENGTH"/> | |
| 118 <option value="E2_BASE_EQUALS_PRIMARY_BASE"/> | |
| 119 <option value="BAM_FILE_MISSING_TERMINATOR_BLOCK"/> | |
| 120 <option value="UNRECOGNIZED_HEADER_TYPE"/> | |
| 121 <option value="POORLY_FORMATTED_HEADER_TAG"/> | |
| 122 <option value="HEADER_TAG_MULTIPLY_DEFINED"/> | |
| 123 <option value="HEADER_RECORD_MISSING_REQUIRED_TAG"/> | |
| 124 <option value="INVALID_DATE_STRING"/> | |
| 125 <option value="TAG_VALUE_TOO_LARGE"/> | |
| 126 <option value="INVALID_INDEX_FILE_POINTER"/> | |
| 127 <option value="INVALID_PREDICTED_MEDIAN_INSERT_SIZE"/> | |
| 128 <option value="DUPLICATE_READ_GROUP_ID"/> | |
| 129 <option value="MISSING_PLATFORM_VALUE"/> | |
| 130 <option value="INVALID_PLATFORM_VALUE"/> | |
| 131 <option value="DUPLICATE_PROGRAM_GROUP_ID"/> | |
| 132 <option value="MATE_NOT_FOUND"/> | |
| 133 <option value="MATES_ARE_SAME_END"/> | |
| 134 <option value="MISMATCH_MATE_CIGAR_STRING"/> | |
| 135 <option value="MATE_CIGAR_STRING_INVALID_PRESENCE"/> | |
| 136 </param> | |
| 137 <param name="max_output" type="integer" value="100" label="The maximum number of lines output in verbose mode" help="MAX_OUTPUT; default=100"/> | |
| 138 <param name="ignore_warnings" type="boolean" label="If true, only report errors and ignore warnings" help="IGNORE_WARNINGS; default=False"/> | |
| 139 <param name="validate_index" type="boolean" checked="True" label="If true and input is a BAM file with an index file, also validates the index" help="VALIDATE_INDEX; default=True"/> | |
| 140 <param name="is_bisulfite_sequenced" type="boolean" label="Whether the SAM or BAM file consists of bisulfite sequenced reads" help="IS_BISULFITE_SEQUENCED; If so, C->T is not counted as an error in computing the value of the NM tag; default=False"/> | |
| 141 | |
| 142 </inputs> | |
| 143 | |
| 144 <outputs> | |
| 145 <data format="txt" name="outFile" label="${tool.name} on ${on_string}: BAM validation summary"/> | |
| 146 </outputs> | |
| 147 | |
| 148 <tests> | |
| 149 <test> | |
| 150 <param name="inputFile" value="picard_ValidateSamFile.bam" ftype="bam"/> | |
| 151 <param name="reference_source_selector" value="history"/> | |
| 152 <param name="ref_file" value="picard_ValidateSamFile_ref.fa"/> | |
| 153 <param name="mode" value="VERBOSE"/> | |
| 154 <param name="ignore" value="INVALID_QUALITY_FORMAT,INVALID_FLAG_PROPER_PAIR"/> | |
| 155 <param name="max_output" value="100"/> | |
| 156 <param name="ignore_warnings" value="Fasle"/> | |
| 157 <param name="validate_index" value="True"/> | |
| 158 <param name="is_bisulfite_sequenced" value="False"/> | |
| 159 <output name="outFile" file="picard_ValidateSamFile_test1.txt" ftype="txt"/> | |
| 160 </test> | |
| 161 </tests> | |
| 162 | |
| 163 <stdio> | |
| 164 <exit_code range="1:" level="warning"/> | |
| 165 </stdio> | |
| 166 | |
| 167 <help> | |
| 168 | |
| 169 **Purpose** | |
| 170 | |
| 171 Reads a SAM/BAM dataset and report on its validity. | |
| 172 | |
| 173 @dataset_collections@ | |
| 174 | |
| 175 @description@ | |
| 176 | |
| 177 MODE=Mode | |
| 178 M=Mode Mode of output Default value: VERBOSE. This option can be set to 'null' to clear the | |
| 179 default value. Possible values: {VERBOSE, SUMMARY} | |
| 180 | |
| 181 IGNORE=Type List of validation error types to ignore. Possible values: {INVALID_QUALITY_FORMAT, | |
| 182 INVALID_FLAG_PROPER_PAIR, INVALID_FLAG_MATE_UNMAPPED, MISMATCH_FLAG_MATE_UNMAPPED, | |
| 183 INVALID_FLAG_MATE_NEG_STRAND, MISMATCH_FLAG_MATE_NEG_STRAND, INVALID_FLAG_FIRST_OF_PAIR, | |
| 184 INVALID_FLAG_SECOND_OF_PAIR, PAIRED_READ_NOT_MARKED_AS_FIRST_OR_SECOND, | |
| 185 INVALID_FLAG_NOT_PRIM_ALIGNMENT, INVALID_FLAG_SUPPLEMENTARY_ALIGNMENT, | |
| 186 INVALID_FLAG_READ_UNMAPPED, INVALID_INSERT_SIZE, INVALID_MAPPING_QUALITY, INVALID_CIGAR, | |
| 187 ADJACENT_INDEL_IN_CIGAR, INVALID_MATE_REF_INDEX, MISMATCH_MATE_REF_INDEX, | |
| 188 INVALID_REFERENCE_INDEX, INVALID_ALIGNMENT_START, MISMATCH_MATE_ALIGNMENT_START, | |
| 189 MATE_FIELD_MISMATCH, INVALID_TAG_NM, MISSING_TAG_NM, MISSING_HEADER, | |
| 190 MISSING_SEQUENCE_DICTIONARY, MISSING_READ_GROUP, RECORD_OUT_OF_ORDER, | |
| 191 READ_GROUP_NOT_FOUND, RECORD_MISSING_READ_GROUP, INVALID_INDEXING_BIN, | |
| 192 MISSING_VERSION_NUMBER, INVALID_VERSION_NUMBER, TRUNCATED_FILE, | |
| 193 MISMATCH_READ_LENGTH_AND_QUALS_LENGTH, EMPTY_READ, CIGAR_MAPS_OFF_REFERENCE, | |
| 194 MISMATCH_READ_LENGTH_AND_E2_LENGTH, MISMATCH_READ_LENGTH_AND_U2_LENGTH, | |
| 195 E2_BASE_EQUALS_PRIMARY_BASE, BAM_FILE_MISSING_TERMINATOR_BLOCK, UNRECOGNIZED_HEADER_TYPE, | |
| 196 POORLY_FORMATTED_HEADER_TAG, HEADER_TAG_MULTIPLY_DEFINED, | |
| 197 HEADER_RECORD_MISSING_REQUIRED_TAG, INVALID_DATE_STRING, TAG_VALUE_TOO_LARGE, | |
| 198 INVALID_INDEX_FILE_POINTER, INVALID_PREDICTED_MEDIAN_INSERT_SIZE, | |
| 199 DUPLICATE_READ_GROUP_ID, MISSING_PLATFORM_VALUE, INVALID_PLATFORM_VALUE, | |
| 200 DUPLICATE_PROGRAM_GROUP_ID, MATE_NOT_FOUND, MATES_ARE_SAME_END, | |
| 201 MISMATCH_MATE_CIGAR_STRING, MATE_CIGAR_STRING_INVALID_PRESENCE} This option may be | |
| 202 specified 0 or more times. | |
| 203 | |
| 204 MAX_OUTPUT=Integer | |
| 205 MO=Integer The maximum number of lines output in verbose mode Default value: 100. This option can | |
| 206 be set to 'null' to clear the default value. | |
| 207 | |
| 208 REFERENCE_SEQUENCE=File | |
| 209 R=File Reference sequence file, the NM tag check will be skipped if this is missing Default | |
| 210 value: null. | |
| 211 | |
| 212 IGNORE_WARNINGS=Boolean If true, only report errors and ignore warnings. Default value: false. This option can | |
| 213 be set to 'null' to clear the default value. Possible values: {true, false} | |
| 214 | |
| 215 VALIDATE_INDEX=Boolean If true and input is a BAM file with an index file, also validates the index. Default | |
| 216 value: true. This option can be set to 'null' to clear the default value. Possible | |
| 217 values: {true, false} | |
| 218 | |
| 219 IS_BISULFITE_SEQUENCED=Boolean | |
| 220 BISULFITE=Boolean Whether the SAM or BAM file consists of bisulfite sequenced reads. If so, C->T is not | |
| 221 counted as an error in computing the value of the NM tag. Default value: false. This | |
| 222 option can be set to 'null' to clear the default value. Possible values: {true, false} | |
| 223 | |
| 224 @more_info@ | |
| 225 | |
| 226 </help> | |
| 227 </tool> | |
| 228 | |
| 229 |
